| SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation | ✓ Link | 70.3 | SegNeXt-L | 2022-09-18 |
| SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation | ✓ Link | 69.9 | SegNeXt-B | 2022-09-18 |
| RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing | | 69.9 | RingMoClaw (Upscale-only TTA) | 2026-09-01 |
| AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation | ✓ Link | 69.3 | AerialFormer-B | 2023-06-12 |
| SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation | ✓ Link | 68.8 | SegNeXt-S | 2022-09-18 |
| AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation | ✓ Link | 68.4 | AerialFormer-S | 2023-06-12 |
| SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation | ✓ Link | 68.3 | SegNeXt-T | 2022-09-18 |
| FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery | ✓ Link | 67.9 | FarSeg++@MiT-B2 | 2023-07-13 |
| FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery | ✓ Link | 67.6 | FarSeg++@ResNet-50 | 2023-07-13 |
| AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation | ✓ Link | 67.5 | AerialFormer-T | 2023-06-12 |
| RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing | ✓ Link | 67.4 | RoMA-B + UperNet (extra data) | 2025-03-13 |
| Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks | | 67.03 | DeepLabV3 with R-50 | 2023-07-26 |
| FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery | ✓ Link | 66.3 | FarSeg++@Swin-T | 2023-07-13 |
| An Empirical Study of Remote Sensing Pretraining | ✓ Link | 65.3 | IMP-ViTAEv2-S-UperNet | 2022-04-06 |
| FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery | ✓ Link | 64.79 | FactSeg@ResNet-50 | 2021-07-27 |
| Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model | ✓ Link | 64.49 | ViTAE-B + RVSA-UperNet | 2022-08-08 |
| An Empirical Study of Remote Sensing Pretraining | ✓ Link | 64.3 | RSP-ViTAEv2-S-UperNet | 2022-04-06 |
| An Empirical Study of Remote Sensing Pretraining | ✓ Link | 64.1 | RSP-Swin-T-UperNet | 2022-04-06 |
| Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model | ✓ Link | 63.85 | ViT-B + RVSA-UperNet | 2022-08-08 |
| Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery | ✓ Link | 63.71 | FarSeg@ResNet-50 | 2020-11-19 |
| An Empirical Study of Remote Sensing Pretraining | ✓ Link | 61.6 | RSP-ResNet-50-UperNet | 2022-04-06 |